AliveCor's AF detection algorithm

San Francisco-based AliveCor has received FDA clearance for two new algorithms for its smartphone-connected ECG: one that detects normality and one that detects interference. These follow up on AliveCor's atrial fibrillation detection algorithm that received clearance last fall.

The Normal Detector assures patients that their ECG is free of abnormalities. If any abnormality is detected, it returns a result of "undetermined." The decision to develop it was based on a poll conducted by AliveCor that found that 9 out of 10 people with heart health issues just want to know if their ECG is normal.

“Our goal for creating these two new detectors was to expand our automated services based on the millions of ECGs now in our database and provide patients with the information they have told us they want at their fingertips,” Euan Thomson, president and CEO of AliveCor, said in a statement. “We know first hand that our customers want the immediate reassurance of knowing when their ECG is normal. With these new detection capabilities, patients, along with their healthcare providers can focus on reviewing those ECGs that are most concerning while also working to understand what lifestyle factors may be contributing to both their normal or abnormal recordings.”

The Interference Detector is about making sure the ECG is returning accurate results, rather than being affected by shaky hands or an overly noisy room. The detector will notify users if there is interference with recording (often called "noise" or "artifact") and prompt them on how best to retake it.

AliveCor’s smartphone ECG, which is available for both Apple and Android smartphones, has had FDA clearance since fall of 2013 and has been in use by patients since March 2013. Last August, the company received clearance for its first algorithm, which detects atrial fibrillation. An app with that algorithm went on sale in September.

Prior to the AFib algorithm, consumers using the device would simply send their ECG readings to a board-certified cardiologist or cardiac technician, who would turn a response around in 24 hours — or faster for a small fee. With the AFib algorithm, patients can take the ECG reading and immediately find out if they have atrial fibrillation. Then they can contact a board-certified cardiologist to confirm the result, and finally take the print out to their own physician.

The algorithm has a 100 percent sensitivity (it never returns a false negative) and a 97 percent specificity (it returns false positives about 3 percent of the time). Earlier this month AliveCor announced that it also received a CE Mark for the atrial fibrillation algorithm and can begin offering it in August.

If these new algorithms follow the timetable of their predecessor, they could launch to the public as soon as next month.

"We actually have a whole suite of algorithms planned to pick out different features of ECGs and different aspects, different diagnoses which we’re working on and we hope to release to the system over time,” Thompson told MobiHealthNews in an interview last year. “And in addition, the way we’d like to move now is toward putting what we call context around the ECG. … So we’d like to move toward gathering information about the patients’ environments and recent history and see if we can spot correlations between unusual features and what’s going on in the patient’s life. But that’s where we’re headed: more clinical conditions, more detailed analysis of the ECG itself, and the context of the ECG and what we can learn from that as well.”